TinyML
BC-ResNet (Broadcasted Residual Network)
Keyword spotting network that mixes 1D temporal and 2D convolutions through broadcasted residual connections to keep accuracy high at small size.
Levelmodel
ClassTinyML
Parametersnot in the notes
Contextnot in the notes
Released8 Jun 2021
Opennessunknown
Runs onmobile or NPU
Statusactive
R&D Topics
Identity
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.
Architecture and Size
- Architecture
- CNN
- Total parameters
- – sources
- Active parameters
- –
- Checkpoint parameters
- –
- Context length
- not in the notes
- Input
- audio
- Output
- labels and boxes
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).
Openness and Access
- Openness
- unknown
- Licence
- not in the notes sources
- Access routes
- not in the notes
Where this comes from
The licence file governs over registry tags and aggregator labels.
Deployment
- Runs on
- mobile or NPU
- Footprint
- The paper targets devices with limited resources such as mobile phones; Silicon Labs MLTK ships a kws_bc_resnet port.
- Runtimes
- not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.
Indonesia
- Indonesian support
- not stated
- Regional languages
- not in the notes
- Jakarta hosting
- unknown
- Languages
- not in the notes
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.
Benchmark Results
The notes record no benchmark result for this model.
Lineage
The notes record no lineage for this model.
Industry Use Cases
No industry use case links this model.
Links
DeveloperQualcommbig tech, USA
Qualcommbig tech, USAModelBC-ResNet (Broadcasted Residual Network)Qualcomm, TinyML
BC-ResNet (Broadcasted Residual Network)Qualcomm, TinyMLUse Casesnone recorded
Who Runs Itnone recorded
Organisations 1
R&D topics 2
Sources
- arxiv.org/abs/2106.04140 https://arxiv.org/abs/2106.04140
- github.com/SiliconLabs/mltk/tree/master/mltk/models/sili... https://github.com/SiliconLabs/mltk/tree/master/mltk/models/siliconlabs
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "BC-ResNet (Broadcasted Residual Network)", https://aurion.semai.id/models/qualcomm-bc-resnet/, records of October 2026.